© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66104
    Prev
    Next
    INDEX
    Explanations

    past time references

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is detecting temporal expressions (dates, months, weekdays, ordinals, and relative time references).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     or
    -1.70
     their
    -1.30
    hline
    -1.16
     a
    -1.13
     provide
    -1.12
     being
    -1.09
     "...
    -1.05
     the
    -1.05
     SizedBox
    -1.03
     unieke
    -1.02
    POSITIVE LOGITS
     but
    1.28
     แต่
    1.27
     peluche
    1.24
     sés
    1.23
     nhưng
    1.21
     الشاشة
    1.15
     mandat
    1.07
    클
    1.07
    Penulis
    1.05
    Didn
    1.05
    Activations Density 0.085%

    No Known Activations